Affiliations: [a] ATR Knowledge Science Laboratories, 2-2-2, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan | [b] Seinan Jo Gakuin University, 1-3-5, Ibori, Kokura, Kitaku, Kitakyushu, Fukuoka 803-0835, Japan | [c] Kyoto Institute of Technology, Matsugasaki, Sakyo-ku, Kyoto 606-8585, Japan | [x] ATR Knowledge Science Laboratories, Japan | [y] School of Engineering, The University of Tokyo, Japan
Abstract: This paper proposes a dynamic prediction procedure that observes nurses' conversations to determine critical points in nursing accidents or incidents. Our previous proposal for this task adopted abduction to logically determine the accident or incident point. However, in this paper we propose a different type of nursing accident or incident determination method. Here, the point is suggested by words or phrases that have certain features. We regard such words or phrases that might cause accidents or incidents as “chances.” This paper analyzes the features of nurses' dialogue and conversation during nursing activities. Based on this analysis, we propose a prototype system that dynamically determines the point where an accident or incident occurs. Accordingly, we aim to deploy this system to achieve better nursing risk management.
